INDEX

Explanations

---------------------- separators

This neuron identifies long runs or lines of repeated dashes (horizontal separator lines).

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

-2.50

とき

-2.45

derdag

-2.44

 категории

-2.42

 ketika

-2.36

 bénéfice

-2.25

有可能

-2.25

・・・・

-2.23

…’

-2.17

POSITIVE LOGITS

↵

2.61

፨

2.48

งิน

2.41

赁

2.41

︲

2.36

Tumor

2.34

 (“

2.34

 стоковая

2.34

頫

2.33

Activations Density 0.042%